24   data.t_id_z = threadIdx.z;  in Interp()
25   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in Interp()
37 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Interp()
51   data.t_id_z = threadIdx.z;  in InterpTranspose()
52   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpTranspose()
64 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTranspose()
78   data.t_id_z = threadIdx.z;  in InterpTransposeAdd()
79   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpTransposeAdd()
91 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTransposeAdd()
107   data.t_id_z = threadIdx.z;  in Grad()
108   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in Grad()
120 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Grad()
134   data.t_id_z = threadIdx.z;  in GradTranspose()
135   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradTranspose()
147 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTranspose()
161   data.t_id_z = threadIdx.z;  in GradTransposeAdd()
162   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradTransposeAdd()
174 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTransposeAdd()
190   data.t_id_z = threadIdx.z;  in Weight()
191   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in Weight()
196 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Weight()